Observability

Analyze cluster observability data and create Grafana dashboards. Use when the user asks about metrics, logs, log labels, cluster health history, dashboards, charts, panels, or visualizations.

43 stars 18 forksDevOps & Cloud

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add NVIDIA/AI-Factory-Operations-Agent --skill observability
Manual install
git clone --depth 1 https://github.com/NVIDIA/AI-Factory-Operations-Agent.git /tmp/AI-Factory-Operations-Agent
mkdir -p ~/.claude/skills
cp -r /tmp/AI-Factory-Operations-Agent/helm/mosaic-stack/files/openclaw-seed/skills/observability ~/.claude/skills/observability

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# observability — Cluster Metrics and Dashboards

Use the `observability_*` and `dashboard_*` tools for read-only cluster metrics and dashboard creation.

Prefer these tools over shell `curl` when answering questions about historical cluster state.

## Useful starting points

- `observability_metric_names` lists available Prometheus or VictoriaMetrics metrics.
- `observability_query` runs an instant PromQL or MetricsQL query supported by the configured backend.
- `observability_range_query` runs a historical range query.
- `dashboard_list` discovers Grafana datasource names, types, and UIDs and searches dashboards.
- `dashboard_create` validates explicit panel PromQL, MetricsQL or LogQL, creates a Grafana dashboard, and opens it in the UI Grafana tab.
- `dashboard_open` opens an existing Grafana dashboard UID in the UI Grafana tab.

For VictoriaMetrics, the same metrics tools use its Prometheus-compatible API.
Use MetricsQL extensions only when the configured metrics backend is VictoriaMetrics.
For dashboards, use the datasource UID and type returned by `dashboard_list`.
VictoriaMetrics may use either `prometheus` or its native
`victoriametrics-metrics-datasource` Grafana plugin. Preserve the discovered type.

## Example PromQL

- `avg by (Hostname) (DCGM_FI_DEV_GPU_UTIL)`
- `max by (Hostname, gpu) (DCGM_FI_DEV_GPU_TEMP)`
- `rate(DCGM_FI_PROF_PCIE_RX_BYTES[5m])`

Treat these as examples only. First use `observability_metric_names` when metric
Read the full skill on GitHub

Details

Skill name
observability
Path
helm/mosaic-stack/files/openclaw-seed/skills/observability/SKILL.md
License
Apache-2.0
Repo updated
17 November 2026

FAQ

What does the Observability skill do?

Analyze cluster observability data and create Grafana dashboards. Use when the user asks about metrics, logs, log labels, cluster health history, dashboards, charts, panels, or visualizations.

How do I install the Observability skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add NVIDIA/AI-Factory-Operations-Agent --skill observability. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Observability popular?

It lives in NVIDIA/AI-Factory-Operations-Agent, which has 43 GitHub stars and 18 forks.

Related skills

AI Factory Operations Agent Headless

43

NVIDIA/AI-Factory-Operations-Agent

Use AI Factory Operations Agent without opening the browser UI. Invoke it through the headless HTTP API, packaged CLI, or stdio MCP server, and deploy it first when no service is available.

AI, LLMs & Agents18

Bcm

43

NVIDIA/AI-Factory-Operations-Agent

Inspect Base Command Manager (BCM) inventory and health evidence, and make explicitly requested changes when Base Command Manager edit mode is enabled.

Other18

GPU Networking

43

NVIDIA/AI-Factory-Operations-Agent

Measure and diagnose distributed GPU networking performance: NCCL collectives, RDMA transport, PCIe topology, link health, IOMMU and ACS. Use for current bandwidth/latency questions and follow-up bottleneck investigations or corrections.

Finance & Crypto18

Cel K8S

45

tyrchen/claude-skills

Write production-ready CEL (Common Expression Language) code for Kubernetes ValidatingAdmissionPolicies, CRD validation rules, and security policies. Use when users need to create admission policies, validate Kubernetes resources, enforce security constraints, or write CEL expressions for Kubernetes.

DevOps & Cloud11

Iraop

43

NVIDIA/AI-Factory-Operations-Agent

Research NVIDIA DGX, SuperPOD, GB200, NVLink, BlueField, Base Command Manager (BCM), and on-prem infrastructure documentation through the IRA/Sequoia retrieval agent. Use when the user asks to research docs, deployment policy, operational guidance, or newly uploaded knowledge-base documents.

DevOps & Cloud18

Kro Rgd Pulumi

45

tyrchen/claude-skills

Create production-ready KRO ResourceGraphDefinitions using Pulumi TypeScript. Use when users need to define custom Kubernetes APIs, compose resources with KRO, integrate AWS ACK resources, or build platform abstractions using Pulumi infrastructure as code.

DevOps & Cloud11

Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.